Monaural source separation is a challenging issue due to the fact that there is only a single channel available; however, there is an unlimited range of possible solutions. In this paper, a monaural source separation model based hybrid deep learning model, which consists of convolution neural network (CNN), dense neural network (DNN) and recurrent neural network (RNN), will be presented. A trial and error method will be used to optimize the number of layers in the proposed model. Moreover, the effects of the learning rate, optimization algorithms, and the number of epochs on the separation performance will be explored. Our model was evaluated using the MIR-1K dataset for singing voice separation. Moreover, the proposed approach achi

HM Al-Dabbas, RA Azeez, AE Ali, Iraqi Journal of Science, 2023

Inspite of the renovation and development that occurred on the

mathematics curricula and its teaching styles (methods), the teaching methods and the evaluation styles that the teachers of the country

follow  are  still  traditionaL It depends  on  the  normal distribution approach and the principle of individual differences among students in

addition the traditional tests that are used to evaluate student achievement are built on standard-referenced system. These types of tests focus on comparing the student's  performance with his peers'

performance. The limitary of this type of evaluation in diagnosing the

students'  acquisition  of  the  stu

Objective:- Women's behavior during pregnancy which can affect the health of their infant , may be influenced by their attitude toward the pregnancy. The study was carried out to assess the pattern of health behaviors for pregnant women. Methodology: A descriptive study was carried out to select randomized (100) pregnant women attending Baghdad Teaching hospital. The data were collected through personal interview by using questionnaire form constructed for the purpose of the study. Results:- The result of the study revealed that the highest percentage of study sample were in age group (21-25) years, primary graduated and house wife . The results showed that the highest percentage( 64%) of them were primigravida, (72%) of them have (1-2)

Background: Recurrent laryngeal nerve injury is
an important post-thyroidectomy complication for
which different modalities of treatment were
practiced to lower its incidence.
Objectives: To estimate the incidence of
recurrent laryngeal nerve injury in thyroid surgeries
in relation to type of surgery, type of gland diseases
& nerve identification.
Methods: Different types of goiters prepared
preoperatively by indirect laryngoscopy, operated
upon with different types of surgeries, postoperative
direct laryngoscopy by the anaesthetist were done
and indirect laryngoscopy done as needed.
Results: Of of 200 patients, the overall incidence
of recurrent laryngeal nerve injury was 9
Patients (4.5%

Most studies combine that it is important to determine the extent of the public's trust TV for two reasons. First of knowing the impact of satellite TV audience ranges and the second determining public outlets for Information Find regard to the extent of the public's confidence in knowing the contents of the satellite during the occupation of Mosul crisis by organizing the Islamic state in Iraq and the Levant And the researcher developed a questionnaire to find out the public's confidence statement satellite contents provided by the questions related to exposandscale.

     The researcher audience chose the city of Baghdad to the suitabil

The purpose of this paper is to identify the statistical indicators of the searched variables and identify the relationship between the cognitive learning outcome and the performance of the two mastering skills by parallel spherical standing and equilibrium on the balance beam. And the identification of the percentage of the cognitive learning outcome contribution to the performance of the two mastering skills by parallel spherical standing and the equilibrium on the balance beam. The two researchers used the descriptive approach in the survey method and the correlational relations, being the most appropriate to the nature of the research problem. The research community for the second stage students in the College of Physical Education and

Sixteen polycyclic aromatic hydrocarbons (PAHs) concentrations were measured in aerosol samples collected for the period from April 2012 to February 2013 at thermal south power station of Baghdad. Fourty one aerosol sample were extracted with (1:1) dichloromethane and methanol using soxhlet for seventeen hour. The extraction solution was analyzed applying GC/MS. The PAH concentrations outside thermal south power station were higher than those inside it, and higher in summer season than in winter. Naphthalene, pyrene, Anthracene, Indeno [1, 2, 3-cd] pyrene and Phenanthrene were the most abundant PAHs detected in all points at the site sampling. The total polycyclic aromatic hydrocarbon (TPAH) and total suspended particles (TSP) concentrat

Objectives: The study intends to identify the sources of work-related stress that might face the nurses working at
psychiatric wards in Baghdad psychiatric hospitals and to find out a relationship between the levels of stress and
some demographic characteristics.
Methodology: A descriptive study was achieved from the 10th of December, 2013 through the 10th of March, 2014.
Non-probability purposive samples of 94 nurses who work in psychiatric wards of Baghdad psychiatric hospitals
were recruited to meet the study objectives. Psychological Stress Inventory (PSI) the Arabic version, which was
modified by Abu Al-Hussein (2010) (20), was used. Data were analyzed by using the statistical analysis program of
SPSS 19th versi

During COVID-19, wearing a mask was globally mandated in various workplaces, departments, and offices. New deep learning convolutional neural network (CNN) based classifications were proposed to increase the validation accuracy of face mask detection. This work introduces a face mask model that is able to recognize whether a person is wearing mask or not. The proposed model has two stages to detect and recognize the face mask; at the first stage, the Haar cascade detector is used to detect the face, while at the second stage, the proposed CNN model is used as a classification model that is built from scratch. The experiment was applied on masked faces (MAFA) dataset with images of 160x160 pixels size and RGB color. The model achieve